Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 15948
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical confinement or restraint

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of extreme physical restraint or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.84
     Effective
    -0.83
    inventoryQuantity
    -0.83
    isSpecialOrderable
    -0.82
     hindsight
    -0.80
    Ô
    -0.77
     Seller
    -0.77
     Crossing
    -0.75
     cance
    -0.74
     Defin
    -0.74
    POSITIVE LOGITS
     torture
    1.49
     tortured
    1.43
     raped
    1.35
     starved
    1.27
     captives
    1.25
     chained
    1.24
     handcuffed
    1.23
     shack
    1.21
     prisoners
    1.20
     raping
    1.16
    Activations Density 0.432%

    No Known Activations